Adaptive, Distribution-Free Prediction Intervals for Deep Networks

Danijel Kivaranovic, Kory Johnson, Hannes Leeb

Publication: Chapter in book/Conference proceedingContribution to conference proceedings


The machine learning literature contains several constructions for prediction intervals thatare intuitively reasonable but ultimately ad-hoc in that they do not come with provableperformance guarantees. We present methods from the statistics literature that can beused efficiently with neural networks underminimal assumptions with guaranteed performance. We propose a neural network thatoutputs three values instead of a single pointestimate and optimizes a loss function motivated by the standard quantile regression loss. We provide two prediction interval methodswith finite sample coverage guarantees solelyunder the assumption that the observations are independent and identically distributed. The first method leverages the conformal in-ference framework and provides average coverage. The second method provides a new, stronger guarantee by conditioning on the observed data. Lastly, our loss function doesnot compromise the predictive accuracy of thenetwork like other prediction interval methods. We demonstrate the ease of use of our procedures as well as its improvements overother methods on both simulated and realdata. As most deep networks can easily be modified by our method to output predictions with valid prediction intervals, its use should become standard practice, much like reporting standard errors along with mean estimates.
Original languageEnglish
Title of host publicationProceedings of the 23rd International Conference on Artificial Intelligence and Statistics
Editors Silvia Chiappa, Roberto Calandra
Place of PublicationOnline
Pages4346 - 4356
Publication statusPublished - 2020

Austrian Classification of Fields of Science and Technology (ÖFOS)

  • 101018 Statistics

Cite this